Vul-Sensitive opcode weighting for multi-label smart contract vulnerability detection

Abstract

The recurring issue of smart contract security breaches has heightened concerns about their reliability and safety, making contract security a critical challenge in the blockchain space. Existing traditional detection techniques predominantly utilize static, expert-defined rule sets, which inherently introduce limitations including reliance on expert knowledge, compromised detection accuracy, and a constrained scope of identifiable vulnerabilities. Therefore, this paper proposes Vul-Sensitive opcode weighting for multi-label smart contract vulnerability detection. The proposed method first processes the source code of smart contracts by converting it to bytecode and then extracts opcodes. Based on a predefined set of critical instructions, Vul-Sensitive opcodes are weighted to enhance the representation of vulnerability-related features. Then, the final feature matrix is utilized by deep learning models for training and classification. To assess the effectiveness of the proposed approach, this paper compares various deep neural network architectures before and after optimization. Experimental results show that it significantly enhances vulnerability detection across all models and consistently outperforms non-weighted methods by effectively strengthening feature representation, achieving the best Micro-F1 score of 90.65%, which validates its effectiveness in multi-vulnerability detection tasks.